Unverified50% confidenceFactExact time
2024年多项学术研究展示了记忆投毒攻击在基于RAG的Agent系统中的可行性，包括通过间接提示注入污染检索语料库的攻击方式
1
Sources
50%
Confidence
Long-term
Relevance
8/18/2026
First Seen
Sources
Related Claims
UnverifiedBy 2024, security researchers had demonstrated indirect prompt injection attacks that hijack RAG system outputs by embedding hidden instructions in web pages74% similarUnverifiedResearchers have reproduced prompt injection attacks on multiple mainstream agent systems, including inducing agents to leak private emails or send messages.65% similarUnverifiedSince 2024, multimodal jailbreak attacks have begun to emerge, with attackers embedding malicious instructions in images or audio to bypass text-level safety detection.64% similarUnverified勒索软件即服务（RaaS）模式起源于2016年前后，核心创新是将攻击能力模块化以订阅或分成方式向附属攻击者开放64% similarUnverifiedThe ua-parser-js incident of 2021 and the node-ipc incident of 2022 demonstrated that attackers can target the entire downstream ecosystem by tampering with dependency packages or injecting malicious dependencies.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/767397API
curl https://kongchang.com/api/v1/knowledge/claims/767397MCP
get_claim(id=767397)